Author

Benedetto Simone

h-index 1 View on Semantic Scholar

We have 2 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Book Open access Nov 2026

LOKI: Dual Domain Perturbation Network for Deepfake Detector Evasion

Deepfake forensic detectors have achieved remarkable performance on pristine synthetic images by exploiting spatial artifacts and frequency-domain inconsistencies. Yet, their reliability degrades substantially under realistic post-processing operations, such as compression, resizing and blurring, which are ubiquitous i...

Michele Nappi, Matteo Polsinelli, Benedetto Simone et al. · 0 citations

#machine learning Preprint Sep 2026

What Did the MLLM Hear? Token-Level Spectro-Temporal Grounding for Audio MLLM Explainability

STAG is introduced, to the authors' knowledge the first post-hoc framework for token-level spectro-temporal grounding of captions generated by audio-based MLLMs, and provides behavioral support for the faithfulness and selectivity of the explanations.

Lucia Cascone, V. Fraenza, Michele Nappi et al. · 0 citations